nm-testing on Hugging Face: model downloads
nm-testing has 514 tracked models, downloaded 1,043,475 times in the last 30 days and 15,967,884 times in total. nm-testing Wrapped: the last 12 months.
Models by downloads in the last 30 days
- nm-testing/SmolLM-1.7B-Instruct-quantized.w4a16 561.1K downloads, text generation
- nm-testing/tinysmokellama-3.2 183.1K downloads, model
- nm-testing/tinysmokeqwen3 82.7K downloads, model
- nm-testing/tinysmokeqwen3moe 29.3K downloads, model
- nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16 17.6K downloads, model
- nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test 8.1K downloads, text generation
- nm-testing/qwen3-8b-peagle-speculators 8K downloads, model
- nm-testing/dflash-qwen3-8b-speculators 7.9K downloads, model
- nm-testing/SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantized 7.6K downloads, model
- nm-testing/Speculator-Qwen3-8B-Eagle3-converted-071-quantized 7.5K downloads, model
- nm-testing/llama2.c-stories15M 7.2K downloads, text generation
- nm-testing/tinysmokeqwen3moe-W4A16-first-only-CTstable 6.7K downloads, model
- nm-testing/Llama-3.2-1B-Instruct-FP8-KV 5.7K downloads, model
- nm-testing/tinyllama-oneshot-w4a16-channel-v2 5K downloads, text generation
- nm-testing/tiny-testing-random-weights 4.9K downloads, model
- nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test 4.3K downloads, model
- nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change 4.2K downloads, text generation
- nm-testing/Speculator-Qwen3-8B-Eagle3-converted-071-quantized-w4a16 3.4K downloads, model
- nm-testing/tinyllama-oneshot-w4a16-group128-v2 3.3K downloads, text generation
- nm-testing/convert_modelopt_nvfp4-e2e 3.1K downloads, text generation
- nm-testing/llama2.c-stories42M-gsm8k-quantized-only-uncompressed 2.6K downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4 2.5K downloads, model
- nm-testing/tinyllama-w4a16-compressed 2.4K downloads, model
- nm-testing/llama2.c-stories15M-ultrachat-mixed-uncompressed 2.3K downloads, model
- nm-testing/llama2.c-stories42M-gsm8k-quantized-only-compressed 2.3K downloads, model
- nm-testing/Llama3_2_1B_speculator.eagle3 2K downloads, model
- nm-testing/Qwen3-30B-A3B-MXFP4A16 1.9K downloads, model
- nm-testing/tinyllama-w8a8-compressed 1.9K downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-kvcache-fp8-tensor 1.8K downloads, model
- nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test 1.7K downloads, text generation
- nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2 1.6K downloads, text generation
- nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2 1.5K downloads, text generation
- nm-testing/llama2.c-stories15M-ultrachat-mixed-compressed 1.5K downloads, model
- nm-testing/testing-llama3.1.8b-2layer-eagle3 1.3K downloads, model
- nm-testing/Llama-3.2-1B-Instruct-quip-w4a16 1.3K downloads, model
- nm-testing/llama2.c-stories110M-gsm8k-recipe_w4a16_actorder_weight-compressed 1.3K downloads, model
- nm-testing/llama2.c-stories110M-gsm8k-fp8_dynamic-compressed 1.2K downloads, model
- nm-testing/tinyllama-fp8-dynamic-compressed 1.2K downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-compressed 1.2K downloads, model
- nm-testing/Qwen3-30B-A3B-FP8-block 1.2K downloads, text generation
- nm-testing/Llama-3.2-1B-Instruct-spinquantR1R2R4-w4a16 1.2K downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-e2e 1.2K downloads, model
- nm-testing/Speculator-Qwen3-8B-Eagle3 1.1K downloads, model
- nm-testing/tinyllama-oneshot-w8-channel-a8-tensor 1.1K downloads, text generation
- nm-testing/llama2.c-stories42M-gsm8k-sparse-only-uncompressed 1.1K downloads, model
- nm-testing/llama2.c-stories42M-gsm8k-stacked-uncompressed 1.1K downloads, model
- nm-testing/Phi-3-mini-128k-instruct-FP8 1.1K downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-MXFP4 1.1K downloads, model
- nm-testing/tinyllama-oneshot-w8a16-per-channel 1.1K downloads, text generation
- nm-testing/Llama-3.2-1B-Instruct-quipv16-nvfp4 1.1K downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-kvcache-fp8-attn_head 1K downloads, model
- nm-testing/Qwen2-1.5B-Instruct-FP8W8 1K downloads, text generation
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-G128-compressed 1K downloads, model
- nm-testing/tinyllama-w8a16-dense 973 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-Asym-Updated-ActOrder 893 downloads, model
- nm-testing/Qwen3-VL-8B-Instruct-W4A16 834 downloads, model
- nm-testing/Qwen3-Coder-30B-A3B-Instruct-W4A16-awq 826 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-compressed 810 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-compressed 805 downloads, model
- nm-testing/Qwen3-30B-A3B-Fp8-v1 757 downloads, model
- nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform 658 downloads, text generation
- nm-testing/Qwen3-VL-8B-Instruct-NVFP4 644 downloads, model
- nm-testing/Mistral-7B-Instruct-v0.3-FP8-Dynamic 594 downloads, model
- nm-testing/llama2.c-stories42M-gsm8k-sparse-only-compressed 592 downloads, model
- nm-testing/llama2.c-stories42M-pruned2.4 585 downloads, model
- nm-testing/llama2.c-stories42M-gsm8k-stacked-compressed 544 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-uncompressed 493 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A16-G128-uncompressed 489 downloads, model
- nm-testing/Qwen2.5-Coder-32B-Instruct-FP8-dynamic 488 downloads, model
- nm-testing/asym-w8w8-int8-static-per-tensor-tiny-llama 481 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-NVFP4A16 453 downloads, model
- nm-testing/convert_awq_w4a16_asym-e2e 417 downloads, text generation
- nm-testing/Kimi-Linear-48B-A3B-Instruct-FP8-DYNAMIC 405 downloads, model
- nm-testing/pixtral-12b-FP8-dynamic 399 downloads, image text to text
- nm-testing/int8_channel_weight_static_per_tensor_act-e2e 387 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-uncompressed 387 downloads, model
- nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-uncompressed 384 downloads, model
- nm-testing/Qwen3-30B-A3B-NVFP4-AWQ-e2e 371 downloads, model
- nm-testing/nvfp4_moe-e2e 365 downloads, model
- nm-testing/kv_cache_fp8-e2e 360 downloads, model
- nm-testing/w4a16_gptq_smoke-e2e 358 downloads, model
- nm-testing/kv_cache_gptq_tinyllama-e2e 333 downloads, model
- nm-testing/fp8_static_per_tensor-e2e 330 downloads, model
- nm-testing/Qwen3-VL-4B-Instruct-NVFP4 323 downloads, model
- nm-testing/Qwen3-Next-80B-A3B-Instruct-NVFP4 315 downloads, model
- nm-testing/qwen36_nvfp4_fp8 314 downloads, model
- nm-testing/fp4_nvfp4-e2e 309 downloads, model
- nm-testing/fp8_weight_only_channel-e2e 292 downloads, model
- nm-testing/w4a16_moe-e2e 288 downloads, model
- nm-testing/w8a8_dynamic_asym-e2e 269 downloads, model
- nm-testing/fp8_weight_only_tensor-e2e 266 downloads, model
- nm-testing/DeepSeek-R1-Distill-Qwen-32B-NVFP4 265 downloads, text generation
- nm-testing/w4a16_actorder_weight-e2e 264 downloads, model
- nm-testing/fp8_dynamic_moe-e2e 262 downloads, model
- nm-testing/model_free_nvfp4a16-e2e 260 downloads, model
- nm-testing/int8_dynamic_per_token-e2e 256 downloads, model
- nm-testing/nvfp4_fp8_mixed-e2e 254 downloads, model
- nm-testing/w8a16_grouped_quant-e2e 253 downloads, model
- nm-testing/w4a16_asym_awq-e2e 252 downloads, model
- nm-testing/multiple_modifiers_gptq_awq-e2e 251 downloads, model